Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9732
    Prev
    Next
    INDEX
    Explanations

    names or phrases with multiple 2-letter combinations that are followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.69
    claw
    -0.66
    Crash
    -0.66
    nces
    -0.64
    anchester
    -0.63
    ðŁij
    -0.62
    furt
    -0.61
    Points
    -0.61
    PsyNetMessage
    -0.59
    Parameters
    -0.59
    POSITIVE LOGITS
    inem
    0.65
    tern
    0.64
    BN
    0.64
    ternity
    0.63
    iste
    0.60
    regation
    0.58
    alg
    0.57
    igma
    0.56
     multim
    0.56
    anced
    0.56
    Activations Density 0.190%

    No Known Activations